-
公开(公告)号：WO2022028805A1
公开(公告)日：2022-02-10
申请号：PCT/EP2021/068888
申请日：2021-07-07
Applicant: ASML NETHERLANDS B.V.
Abstract: Method and apparatus for adapting a distribution model of a machine learning fabric. The distribution model is for mitigating the effect of concept drift, and is configured to provide an output as input to a functional model of the machine learning fabric. The functional model is for performing a machine learning task. The method comprises obtaining a first data point, and providing the first data point as input to one or more distribution monitoring components of the distribution model. The one or more distribution monitoring components have been trained on a plurality of further data points. A metric representing a correspondence between the first data point and the plurality of further data points is determined, by at least one of the one or more distribution monitoring components. Based on the error metric, the output of the distribution model is adapted.
-
2.发明申请
公开(公告)号：WO2021197730A1
公开(公告)日：2021-10-07
申请号：PCT/EP2021/054988
申请日：2021-03-01
Applicant: ASML NETHERLANDS B.V.
Inventor： KOULIERAKIS, Eleftherios , LANCIA, Carlo , GONZALEZ HUESCA, Juan Manuel , YPMA, Alexander , GKOROU, Dimitra , SAHRAEIAN, Reza
IPC: G03F7/20 , G03F7/705 , G03F7/70525
Abstract: Described is a method for determining an inspection strategy for at least one substrate, the method comprising: quantifying, using a prediction model, a compliance metric value for a compliance metric relating to a prediction of compliance with a quality requirement based on one or both of pre- processing data associated with the substrate and any available post-processing data associated with the at least one substrate; and deciding on an inspection strategy for said at least one substrate, based on the compliance metric value, an expected cost associated with the inspection strategy and at least one objective value describing an expected value of the inspection strategy in terms of at least one objective relating to the prediction model.
-
Patent Agency Ranking3.发明公开
公开(公告)号：EP4127834A1
公开(公告)日：2023-02-08
申请号：EP21707304.8
申请日：2021-03-01
Applicant: ASML Netherlands B.V.
Inventor： KOULIERAKIS, Eleftherios , LANCIA, Carlo , GONZALEZ HUESCA, Juan Manuel , YPMA, Alexander , GKOROU, Dimitra , SAHRAEIAN, Reza
IPC: G03F7/20
-
4.发明公开
公开(公告)号：EP4209846A1
公开(公告)日：2023-07-12
申请号：EP22150693.4
申请日：2022-01-10
Applicant: ASML Netherlands B.V.
Inventor： KOULIERAKIS, Eleftherios , GANTAPARA, Anjan Prasad , KHEDEKAR, Satej, Subhash , ROSTAMI, Hamideh
Abstract: A computer-implemented method for training a diagnostic model for diagnosing a production system, wherein the production system comprises a plurality of sub-systems. The adaptive diagnostic model comprises, for each sub-system, a corresponding first learning model arranged to receive input data, and to generate compressed data for the production system in a corresponding compressed latent space. A second learning model is arranged to receive the compressed data generated by the first learning models, and generate further compressed data for the production system in a further compressed latent space. The method comprises performing unsupervised training of the first and second learning models based on training data derived from sensor data characterizing the sub-systems.
-
公开(公告)号：EP3961518A1
公开(公告)日：2022-03-02
申请号：EP20192534.4
申请日：2020-08-25
Applicant: ASML Netherlands B.V.
Abstract: Method and apparatus for adapting a distribution model of a machine learning fabric. The distribution model is for mitigating the effect of concept drift, and is configured to provide an output as input to a functional model of the machine learning fabric. The functional model is for performing a machine learning task. The method comprises obtaining a first data point, and providing the first data point as input to one or more distribution monitoring components of the distribution model. The one or more distribution monitoring components have been trained on a plurality of further data points. A metric representing a correspondence between the first data point and the plurality of further data points is determined, by at least one of the one or more distribution monitoring components. Based on the error metric, the output of the distribution model is adapted.
-
公开(公告)号：EP4343472A1
公开(公告)日：2024-03-27
申请号：EP22196685.6
申请日：2022-09-20
Applicant: ASML Netherlands B.V.
Inventor： KOULIERAKIS, Eleftherios , GONZALEZ HUESCA, Juan Manuel , SMAL, Pavel , AARDEN, Frans, Bernard , RAVICHANDRAN, Arvind , DOU, Meng , HUBAUX, Arnaud , VAN HERTUM, Pieter
IPC: G05B19/418
Abstract: One embodiment relates to a method of classifying product units subject to a process performed by an apparatus, the method comprising: receiving KPI data, the KPI data associated with a plurality of components of the apparatus and comprising data associated with a plurality of KPIs; clustering the KPI data to identify a plurality of clusters; analyzing the plurality of clusters to identify a plurality of failure modes associated with the apparatus, for each identified failure mode assigning a threshold to each KPI associated with the failure mode; and for each of the plurality of product units: determining the likelihood of each of the plurality of failure modes based on KPI data of the product unit and the thresholds assigned to each KPI associated with one of the plurality of failure modes; and performing a classification based on the likelihoods of each of the plurality of failure modes.
-
7.发明公开
公开(公告)号：EP3910417A1
公开(公告)日：2021-11-17
申请号：EP20174335.8
申请日：2020-05-13
Applicant: ASML Netherlands B.V.
IPC: G03F7/20
Abstract: Described is a method and associated computer program and apparatuses for method for making a decision as to whether to inspect a substrate from a group of substrates within a manufacturing process. The method comprises assigning to each substrate of the group of substrates, a probability value describing a probability of complying with a quality requirement, using a model trained to predict compliance with the quality requirement based on pre-processing data associated with the substrate; and deciding whether to inspect each substrate based on the probability value and one or both of: an expected cost of the inspection step and at least one objective value describing an expected value of inspecting the substrate in terms of at least one objective relating to the model.
-
-
-
-
-
-
Search Results
7
records
(took 0.023 seconds)
